Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4103 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.6995. Min Act: -0.1700
Data Index: 7526046 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.6058. Min Act: -0.1700
Data Index: 6323343 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.5745. Min Act: -0.1700
Data Index: 501522 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.5120. Min Act: -0.1700
Data Index: 1271256 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.5120. Min Act: -0.1700
Data Index: 4150290 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.5120. Min Act: -0.1700
Data Index: 6425337 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.4495. Min Act: -0.1700
Data Index: 1903453 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.4183. Min Act: -0.1700
Data Index: 5473363 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.4183. Min Act: -0.1700
Data Index: 3638595 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.4183. Min Act: -0.1700
Data Index: 1500713 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.4183. Min Act: -0.1700
Data Index: 6298953 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.4495. Min Act: -0.1700
Data Index: 1561075 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.3870. Min Act: -0.1700
Data Index: 4150287 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.3870. Min Act: -0.1700
Data Index: 6197272 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.3870. Min Act: -0.1700
Data Index: 2537159 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.3870. Min Act: -0.1700
Data Index: 2218966 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.3870. Min Act: -0.1700
Data Index: 6340154 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.3558. Min Act: -0.1700
Data Index: 1271255 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.3558. Min Act: -0.1700
Data Index: 2653132 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6995. Min Range: -5.6995
Max Act: 5.3558. Min Act: -0.1700
Data Index: 2178529 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19